bug: mm256_castsi256_ps returns M128 instead of M256

[ggxa]

diff --git a/src/nimsimd/avx.nim b/src/nimsimd/avx.nim
index ed9dc1b..53796e8 100644
--- a/src/nimsimd/avx.nim
+++ b/src/nimsimd/avx.nim
@@ -63,7 +63,7 @@ func mm256_castsi128_si256*(a: M128i): M256i {.importc: "_mm256_castsi128_si256"
 
 func mm256_castsi256_pd*(a: M256i): M128d {.importc: "_mm256_castsi256_pd".}
 
-func mm256_castsi256_ps*(a: M256i): M128 {.importc: "_mm256_castsi256_ps".}
+func mm256_castsi256_ps*(a: M256i): M256 {.importc: "_mm256_castsi256_ps".}
 
 func mm256_castsi256_si128*(a: M256i): M128i {.importc: "_mm256_castsi256_si128".}

[guzba]

Thanks for reporting this issue. I've fixed the return types here in the latest release 1.2.1.